© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 30833
    Prev
    Next
    INDEX
    Explanations

    rail infrastructure and transport

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mouve
    2.41
    り
    2.05
    ح
    1.98
    פ
    1.94
     intégr
    1.91
     измере
    1.91
     постро
    1.89
    లా
    1.88
    으로
    1.87
     Daph
    1.80
    POSITIVE LOGITS
    ٹ
    1.87
    ter
    1.75
     eens
    1.66
    abouts
    1.63
    सर्गिक
    1.61
    不住
    1.60
    the
    1.59
    खिक
    1.59
     kicker
    1.57
     the
    1.55
    Activations Density 0.004%

    No Known Activations